Model Builder
Inspect & challenge the published model
Take a whack at the published model. Add or remove predictors, refit on a subgroup, or build a model from scratch from the same survey data.
The published model — Electric Insights' release-day explanatory account of Kennedy's approval — remains the released account; this tool exists so anyone can inspect, challenge, or extend it. The six published predictors are pre-selected to start.
How to Use This Tool
Not sure where to start? The published model is already loaded — pick an outcome at the top, then click Run Analysis at the bottom to see how it performs.
How to Use This Tool
Not sure where to start? The published model is already loaded — pick an outcome at the top, then click Run Analysis at the bottom to see how it performs.
1. Choose an Outcome
Pick what your model is predicting: Presidential Approval, Vote Intention (Kennedy vs. Goldwater), or Tax Cut Support. Each outcome is a binary measure (1 = yes, 0 = no).
2. Choose a Subgroup (Optional)
By default, the model is fit on all respondents. Optionally restrict it to one subgroup at a time — e.g. just Republicans, or just respondents under 35 — to see how the model behaves within that group. Subgroup levels with fewer than 100 respondents are hidden.
3. Select Predictors
Check the survey questions you want to test as predictors. The six published-model predictors are pre-selected by default. You can add or remove any — up to 20 for Run Analysis. Hover the icons for plain-English definitions.
4. Add a Synthetic Variable (Optional)
Check Configure Synthetic Variable to add a hypothetical predictor — one not measured in the survey but theoretically possible. You set how strongly it should correlate with the outcome and how different it should be from existing predictors. After running, the results show whether this imaginary variable would have improved the model, and which real survey questions come closest to capturing the same signal.
5. Run Analysis or Auto-Build
Run Analysis is the primary tool — it builds a model from exactly the variables you selected. Use it when you want full control.
Auto-Build Standard searches all available variables automatically and selects those that most improve predictive fit. Useful as a benchmark.
Auto-Build Actionable Predictors applies an additional constraint: it weights selection toward variables that can be moved by policy or communication (e.g. issue evaluations) over fixed demographic context (e.g. age, race). The result is a model suited for strategic interpretation.
Auto-Build does not use a synthetic variable. To add one, run Auto-Build first to identify the best predictor set, then re-run with Run Analysis with the synthetic variable enabled.
6. Review Results
Results show how well the model predicts the outcome and how much each predictor contributes. The Other Variables in This Survey section below the results lists every variable not yet in your model — each card shows whether adding it would likely improve fit. Click Add to model on any card to include it, then re-run.
7. Use the Simulator
After running, click Launch in the Simulator panel to open an interactive tool. Set any combination of survey responses — for example, set the economy rating to "Poor" and Vietnam handling to "Excellent" — and see the predicted approval probability update instantly.
8. Iterate and Compare
Each run is saved automatically in the Saved Analyses tray. Click Load on any saved card to restore that run's variables and settings. Use Compare to view two runs side by side — each card shows three scores: Tjur R² (how well the model separates approvers from non-approvers), AUC (overall predictive accuracy), and Brier (calibration error — lower is better). Higher Tjur R² and AUC and lower Brier means a better-performing model.
Understanding Your Results
After running your analysis, results are organized into up to three sections:
Full Model
Complete model including all selected predictors and the synthetic variable, if configured.
Base Model
Model performance without the synthetic variable (appears only when one is configured).
Synthetic Variable Performance
How well the synthetic variable met its specifications and its impact on model performance (appears only when one is configured).